EXCELLERAT’s latest workshop dealt with data analysis for engineering data, particularly simulation data. Partners from Fraunhofer SCAI conducted this one-day online training course with sessions dedicated to the topics of Clustering, Dimensionality Reduction, Pre-processing of Simulation Data, and two hands-on tutorials with exemplary use-cases from car crash analysis and aeroacoustics.
The eight workshop participants were partners and guests from HLRS, KTH, SSC-Services, and University of Trier, who actively contributed to the workshop by eagerly asking questions, initiating important discussions, and experimenting with the introduced data analysis tools in the hands-on sessions.
The workshop aimed to bridge a gap between the important topics of numerical computations, data analysis, and state-of-the-art machine learning. During the course, the participants got to discover new ways of analysing, compressing, and also visualising bundles of simulation data in order to allow for an efficient analysis of variations of physical quantities of interest. Furthermore, the introduced methods served as a tool to detect the influence of input parameters on the outcome of different simulations. The overall goal of this approach is to reduce the number of necessary computations of expensive large-scale numerical simulations.
“The workshop was great, starting from simple classification methods to real engineering applications. The part on nonlinear dimension reduction was challenging and I wish there will be another workshop on this. Also reinforcement learning and distributed Machine Learning and Deep Learning are ‘hot’ topics worth a further workshop”, said Lorenzo Zanon who participated in the workshop.
EXCELLERAT aims to offer further workshops at the intersection of data analytics and numerical simulations in the future, as there is great interest in these topics. The training material is available online.
Learn more about EXCELLERAT’s training offerings: https://services.excellerat.eu/searchevents/training